# About Normalization using pre-trained vgg16 networks

**URL:** <https://discuss.pytorch.org/t/about-normalization-using-pre-trained-vgg16-networks/23560>\
**Category:** Uncategorized\
**Created:** [August 21, 2018, 5:59am UTC](https://discuss.pytorch.org/t/about-normalization-using-pre-trained-vgg16-networks/23560 "2018-08-21T05:59:03Z")\
**Posts on this page:** 1\
**Showing post:** 18

<div class="post-metadata">

**Author:** ![amit\_js](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/amit_js/32/12391_2.png) [@amit\_js](https://discuss.pytorch.org/u/amit_js)\
**Post date:** [May 14, 2020, 5:45pm UTC](https://discuss.pytorch.org/t/about-normalization-using-pre-trained-vgg16-networks/23560/18 "2020-05-14T17:45:39Z")

</div>

Hi @ptrblck,  
std can’t be added and then averaged to get the overall std, please have a look at this,[https://stackoverflow.com/a/60803379/8063334](https://stackoverflow.com/a/60803379/8063334)

---

_[View the full topic](https://discuss.pytorch.org/t/about-normalization-using-pre-trained-vgg16-networks/23560)._